Dongsoo Lee

Orcid: 0000-0002-6730-7125

According to our database1, Dongsoo Lee authored at least 50 papers between 2011 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization.
CoRR, 2024

DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation.
CoRR, 2024

32.2 A 24.25-to-29.5GHz Extremely Compact Doherty Power Amplifier with Differential-Breaking Phase Offset Achieving 23.7% PAEavg for 5G Base-Station Transceivers.
Proceedings of the IEEE International Solid-State Circuits Conference, 2024

2023
V-LSTM: An Efficient LSTM Accelerator Using Fixed Nonzero-Ratio Viterbi-Based Pruning.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., October, 2023

Machine learning-based quantification for disease uncertainty increases the statistical power of genetic association studies.
Bioinform., September, 2023

Fully Parallel, One-Cycle Random Shuffling for Efficient Countermeasure in Post-Quantum Cryptography.
IACR Cryptol. ePrint Arch., 2023

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models.
CoRR, 2023

Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Information Geometry of the Retinal Representation Manifold.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization.
Proceedings of the International Conference on Machine Learning, 2023

Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

TF-MVP: Novel Sparsity-Aware Transformer Accelerator with Mixed-Length Vector Pruning.
Proceedings of the 60th ACM/IEEE Design Automation Conference, 2023

2022
nuQmm: Quantized MatMul for Efficient Inference of Large-Scale Generative Language Models.
CoRR, 2022

Maximum Likelihood Training of Implicit Nonlinear Diffusion Models.
CoRR, 2022

Maximum Likelihood Training of Implicit Nonlinear Diffusion Model.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Augmenting Magnetic Resonance Imaging with Tabular Features for Enhanced and Interpretable Medial Temporal Lobe Atrophy Prediction.
Proceedings of the Machine Learning in Clinical Neuroimaging - 5th International Workshop, 2022

Volume is All You Need: Improving Multi-task Multiple Instance Learning for WMH Segmentation and Severity Estimation.
Proceedings of the Machine Learning in Clinical Neuroimaging - 5th International Workshop, 2022

Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression.
Proceedings of the Tenth International Conference on Learning Representations, 2022

DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation.
Proceedings of the 2022 IEEE Hot Chips 34 Symposium, 2022

AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

2021
Modulating Regularization Frequency for Efficient Compression-Aware Model Training.
CoRR, 2021

Sequential Encryption of Sparse Neural Networks Toward Optimum Representation of Irregular Sparsity.
CoRR, 2021

Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization.
CoRR, 2021

A mechanistically interpretable model of the retinal neural code for natural scenes with multiscale adaptive dynamics.
Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, 2021

2020
BiQGEMM: matrix multiplication with lookup table for binary-coding-based quantized DNNs.
Proceedings of the International Conference for High Performance Computing, 2020

FleXOR: Trainable Fractional Quantization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

Structured Compression by Weight Encryption for Unstructured Pruning and Quantization.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

A Review of On-Device Fully Neural End-to-End Automatic Speech Recognition Algorithms.
Proceedings of the 54th Asilomar Conference on Signals, Systems, and Computers, 2020

2019
Learning Low-Rank Approximation for CNNs.
CoRR, 2019

Structured Compression by Unstructured Pruning for Sparse Quantized Neural Networks.
CoRR, 2019

Network Pruning for Low-Rank Binary Indexing.
CoRR, 2019

Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
DeepTwist: Learning Model Compression via Occasional Weight Distortion.
CoRR, 2018

Retraining-Based Iterative Weight Quantization for Deep Neural Networks.
CoRR, 2018



Viterbi-based Pruning for Sparse Matrix with Fixed and High Index Compression Ratio.
Proceedings of the 6th International Conference on Learning Representations, 2018

2017
Security of Stateful Order-Preserving Encryption.
Proceedings of the Information Security and Cryptology - ICISC 2017 - 20th International Conference, Seoul, South Korea, November 29, 2017

Forward Secure Dynamic Searchable Symmetric Encryption with Efficient Updates.
Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, 2017

2016
Embedding Read-Only Memory in Spin-Transfer Torque MRAM-Based On-Chip Caches.
IEEE Trans. Very Large Scale Integr. Syst., 2016

Optimal wavelength provisioning with fuzzy logic control for power saving in TWDM-PONs.
Proceedings of the International Conference on Information and Communication Technology Convergence, 2016

2014
Design and Optimization of Multiple-Mesh Clock Network.
Proceedings of the VLSI-SoC: Internet of Things Foundations, 2014

2013
Area Efficient ROM-Embedded SRAM Cache.
IEEE Trans. Very Large Scale Integr. Syst., 2013

Fast management of ONUs based on broadcast control channel for a 10-gigabit-capable passive optical network (XG-PON) system.
J. Commun. Networks, 2013

2012
Soft-Error-Resilient FPGAs Using Built-In 2-D Hamming Product Code.
IEEE Trans. Very Large Scale Integr. Syst., 2012

Viterbi-Based Efficient Test Data Compression.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2012

High-performance low-energy STT MRAM based on balanced write scheme.
Proceedings of the International Symposium on Low Power Electronics and Design, 2012

2011
Memory-based embedded digital ATE.
Proceedings of the 29th IEEE VLSI Test Symposium, 2011

Column-selection-enabled 8T SRAM array with ~1R/1W multi-port operation for DVFS-enabled processors.
Proceedings of the 2011 International Symposium on Low Power Electronics and Design, 2011


  Loading...